© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2075
    Prev
    Next
    INDEX
    Explanations

    登場 or 決定

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ಂಥ
    0.50
    ⵚ
    0.50
     rigu
    0.49
     nisid
    0.47
     maniak
    0.47
    .|__
    0.46
     那麼
    0.46
     平成
    0.46
     wollten
    0.46
    ẳn
    0.45
    POSITIVE LOGITS
    ID
    0.45
    J
    0.43
    List
    0.41
    -
    0.41
    ↵
    0.40
    Id
    0.40
    Z
    0.40
    X
    0.40
    0.39
    Grade
    0.39
    Activations Density 0.007%

    No Known Activations